Showing papers on "Node (networking) published in 1975"

Data sharing computer network

Abstract: A data communication network having a plurality of nodes interconnected with a communication link, wherein each node shares given ones of its data sets in common with other nodes in the network, and each node is operative to update any shared data set, except if one of the other nodes is also seeking to update the same data set, in which case the node having the higher priority prevails. Each node has a memory which stores the node location of each shared data set and the updating priority which each node has with respect to each respective set of shared data. A node receiving competing requests for update will access this memory and, depending upon the sequence of the requests, may accept a higher priority request and refuse a lower priority request.

Node listings applied to data flow analysis

Abstract: A new approach to global program data flow analysis which constructs a "node listing" for the control flow graph is discussed and a simple algorithm which uses a node listing to determine the live variables in a program is presented. This algorithm combined with a fast node listing constructor due to Aho and Ullman has produced an 0(n log n) algorithm for live analysis. The utility of the node-listing method is demonstrated by an examination of the class of graphs for which "short" listings exist. This class is quite similar to the class of graphs for "understandable" programs.

ALOHA packet broadcasting - A retrospect

Abstract: Packet broadcasting is a technique whereby data is sent from one node in a net to another by attaching address information to the data to form a packet---typically from 30 to 1000 bits in length. The packet is then broadcast over a communication channel which is shared by a large number of nodes in the net; as the packet is received by these nodes the address is scanned and the packet is accepted by the proper addressee (or addressees) and ignored by the others. The physical communication channel employed by a packet broadcasting net can be a ground based radio channel, a satellite transponder or a cable.

Communications network for general purpose data communications in a heterogeneous environment

Abstract: A data communication network system for interconnecting a group of heterogeneous computers, batch terminals and conversational terminals employing serial transmission techniques in a ring or loop configuration. Each computer or terminal is connected to the communication network via communications processor and a interface unit termed a node. The communications processor is responsible for network protocol and activities as well as for interfacing devices to the network. The node provides the only connection to the ring or loop and derives the clock for the communications processor as well as the node itself from the transmitted data. All information in the communication network is transmitted in a modified Mauchly format and will appear as n-bit data or control characters. A control character, which always precedes a data character, will either be the address of a node or a null. To read information from the network, the node must detect a control character which represents its address. To insert information into the network the node must detect a control character which represents a null. Communications between loops or rings is always via nodes.

Data communications loop synchronizer

Abstract: A loop controller for a data communication network system formed by interconnecting a group of heterogeneous computers, batch terminals and conversational terminals in a ring or loop configuration. Each computer or terminal is connected to the communication network via a communications processor and an interface unit termed a node. The communications processor is responsible for network protocol and activities as well as for interfacing devices to the network. The node provides the only connection to the ring or loop and derives the clock for the communications processor as well as the node itself from the transmitted data. The logocontroller combines timing signals and information signals and forms a sequential stream of alternating control and data characters, each character being n-bits in length. This stream is then placed on the loop for serial transmission to the individual nodes connected to the loop. Signals received by the loop controller are synchronized for retransmission back to the loop.

Method of data communications in a heterogenous environment

Abstract: A method of data communications for use in systems employing serial transmission techniques in a ring or loop configuration. Access to the communication network is via a communications processor and a interface unit termed a node. The communications processor is responsible for network protocol and activities as well as for interfacing devices to the network. The node provides the only connection to the loop and drives the clock for the communications processor as well as the node itself from the transmitted data. All information in the communication network is transmitted in a modified Mauchly format and will appear as n-bit data or control characters. A binary ONE is represented as a signal level transition from one level to another, while a binary ZERO is represented by an opposite signal transition. A control character, which always precedes a data character, will either be the address of a node or a null. To read information from the network, the node must detect a control character which represents its address. To insert information into the network the node must detect a control character which represents a null.

Transaction Processing in the Common Node of a Distributed Function Laboratory Computer System

Abstract: A computer network architecture consisting of a common node processor for managing peripherals and files and a number of private node processors for laboratory experiment control is briefly reviewed. Central to the problem of private node-common node communication is the concept of a transaction. The collection of procedures and the data structures associated with a transaction are described. The common node properties assigned to a transaction and procedures required for its complete processing are discussed.

A Node Method for Multiparametric Linear Programming

Abstract: A method is presented for the generation of extreme points of regions in the parameter space for which a certain basic solution is optimal. It is shown that for any extreme point the inequalities which determine the adjacent regions are easily generated. A numerical example is worked out in detail.

Equilibrium Properties of Arbitrarily Interconnected Queueing Networks.

Abstract: : Considered are properties of arbitrarily interconnected queueing networks of single server nodes with exponential service and Poisson exogenous inputs. Customers departing node i are instantaneously routed to node j with probability (p sub ij), or depart the system with probability (q sub i).

Distributed computer networks

Abstract: How desirable and inevitable are large heterogeneous, distributed computer networks? In this article Professor Kirstein, whose group at University College London operates one node of the large international ARPA network, describes the motivation for setting up such networks and the problems which must be resolved before they are deployed more widely. Those problems are often more political and sociological than technical.

Optimal allocation of resources in distributed information networks

Abstract: The problems of file allocation and capacity assignment in a fixed topology distributed computer network are examined. These two aspects of the design are tightly coupled through an average message delay constraint. The objective is to allocate copies of information files to network nodes and capacities to network links so that a minimum cost is achieved subject to network delay and file availability constraints. A model for solving the problem is formulated and the resulting optimization problem is shown to fall into a class of non-linear integer programming problems. Deterministic techniques for solving this class of problems are computationally cumbersome even for small sized problems. A new heuristic algorithm is developed, based on a decomposition technique which greatly reduces the computational complexity of the problem. Numerical results for a variety of network configurations indicate that the heuristic algorithm, while not theoretically convergent, yields practicable low cost solutions with substantial savings in computer processing time and storage requirements. Moreover, it is shown that this algorithm is capable of solving realistic network problems whose solution using deterministic techniques is computationally intractable.

Heuristic Methods for Solving Large Scale Network Routing Problems: The Telpaking Problem

Abstract: An approach to a large scale network routing problem with nonlinear cost function is described, along with an example of its application. The approach to the problem involves a multistage construction process. This approach is applied to the telpaking problem. Results are obtained in applying this method to a 53 node sample problem.

Public transport assignment calculations with the transcom suite

Abstract: This consideration of the important features of Transcom describes the techniques for the computerized version of a network as well as the assignment calculations (as an example of the utilisation of the computerized version). The transit network information structure framework is described and the details are discussed of its principal concepts: zone, centroid, link, node, section and lines. The details are given of the assignment method which involves a minimum travel time tree where the travel time between 2 nodes is defined by an impedance function. The methods presented here have been implemented in the Montreal Urban Community Transportation Commission network which consists of 3 metro lines and 115 bus lines with 600 nodes in the network.

Structure, Evaluation, and Control of Decision Activity Networks.

Abstract: : A new approach for handling special decision networks is presented. This approach also allows for optimally controlling the corresponding projects. Decision networks are activity networks with several kinds of nodes, and with each arc is associated the probability that the corresponding activity is performed, and the duration of the activity, a nonnegative random variable. Three possible entrance sides (and, exclusive-or, inclusive-or) and two exit sides (deterministic, stochastic) of a node and hence six different node types are considered satisfying a so-called 'node logic'.

A Node Elimination Method For Finding Negative Cycles In A Directed Graph

Abstract: A new method for locating and tracing negative cycles in a directed graph is presented. The method is based on the idea of node-eliminations, which means simply isolating a notde from the graph and...

Hybrid Computer Simulation Study of Adaptive Routing Techniques for Switching Networks to Enhance Survivability for Optimum System Performance.

Abstract: : This report documents the results of a twelve month study of routing and control techniques to enhance the survivability and performance of circuit switched networks. Major emphasis has been placed on the investigation of European Autovon with respect to given scenarios and control actions. A primary and significant output of this study has been a fast, flexible hybrid computer simulation program. This call-by-call simulation incorporates five-level priority calling, four-level preemption, and scenario/control action mechanisms. The network chosen for this study was a 10 node network similar to the European Autovon with the Conus Gateway switches modeled as one additional node. Twenty-six links were simulated including the three Conus Gateway links. Original capacity of the model was 15 nodes (including the Conus Gateway node) and 48 links. Calls were generated on a call-by-call basis using actual traffic loading data from the European Autovon to drive nonlinear functions for call hold times and time between calls.

Node synchronization in a distributed computer network

Abstract: In a distributed control network, questions such as: “Between two messages arriving at a node, which one left its original node first?”, or “How much time elapsed in the trip of a message between two remote nodes?” are relevant points for many specific problemsA realistic approach to the problem of the “Common Time”, not requiring external time source, is based on the fact that appropriate messages carrying time information flow between adjacent nodes, with a known delay.The model discussed in this paper is based on this hypothesis.